Kerry Back
For a neuron with
\[ y = \max(0, b + w_1x_1 + \cdots + w_n x_n)\]
There are many ways to take care of outliers and scaling, but we’ll just use one.
Distribution before (old) and after (new)
from sqlalchemy import create_engine
import pymssql
import pandas as pd
server = "mssql-82792-0.cloudclusters.net:16272"
username = "user"
password = "" # paste password between quote marks
database = "ghz"
string = "mssql+pymssql://" + username + ":" + password + "@" + server + "/" + database
conn = create_engine(string).connect()
Later:
Comments